Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds important behavioral context beyond these: the conditional dual-mode behavior (retrieve vs. list when key is omitted) and the scoping mechanism ('Scoped to your identifier'). This supplements the annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each serving a distinct purpose: defining the operation, giving the usage context, and explaining scoping. It is front-loaded with the core action and avoids fluff or redundancy. No sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having no output schema, the description adequately covers the tool's behavior, scoping, and relationship to siblings. It explains both modes (retrieve by key, list by omission) and provides sufficient context for an agent to correctly select and invoke the tool. The tool is simple, and the description leaves no critical gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage of the 'key' parameter, including its optionality and the list-all behavior when omitted. The description adds value by giving real-world examples of what keys might contain ('the user's target ticker, an address, prior research notes') and clarifying that the value was 'previously saved via remember,' which enriches the semantics beyond the schema's mechanical definition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states both functions: retrieving a saved value by key and listing all keys when the key is omitted. It uses specific verbs ('retrieve', 'list') and explicitly ties the tool to its sibling tools ('remember' and 'forget'), distinguishing it from other tools in the list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool: 'Use to look up context the agent stored earlier' with concrete examples (target ticker, address, research notes). It also implicitly contrasts with 'remember' (save) and 'forget' (delete) by saying 'Pair with remember to save, forget to delete,' giving clear guidance on alternative tools for different operations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.